Extract full-sized photos from photos.live.com using rss feed

photosliveextract.py

#! /usr/bin/python2
#
# Gaute Hope <eg@gaute.vetsj.com> 2011
#
# Extract full-size photos from photos.live.com using rss feed
#
# Requires: - feedparser: http://feedparser.org/ - Python 2


VERSION = 1

print "photosliveextract - v", VERSION

feeduri = ''
outdir = 'extracted/'

import os
import sys
import time

if not os.path.exists (outdir):
  os.makedirs (outdir)

import feedparser
import urllib

# load feed
sys.stdout.write ('loading feed..: ' + feeduri)
sys.stdout.flush ()
feed = feedparser.parse (feeduri)
sys.stdout.write (' - done.\n')

items = feed.items()[9][1]

offset = 0 # 0 indexed [in case you don't want to start at the first
           # photo]
index = offset
items = items[offset:]

failed = 0

print "Downloading:", len(items), "items."

for i in items:
  tries = 50
  while tries:
    try:
      sys.stdout.write ('[' + str(index) + "/" + str(len(items)) + '] downloading: ' + i['title'] + '..')
      sys.stdout.flush ()

      # get page
      p = urllib.urlopen (i['link']).read ()
      start = p.find ('<a id="spPreviewLink" href="')
      end   = p.find ('" rel="nofollow"', start)
      photouri = p[start+28:end].replace('&#58;',':').replace('&#63;','?').replace('&#61;','=')
      sys.stdout.write (': ' + photouri + ' ..')
      sys.stdout.flush ()

      # get photo
      urllib.urlretrieve (photouri, os.path.join (outdir, i['title']))
      sys.stdout.write ('done.\n')

      urllib.urlcleanup ()
      tries = 0
    except:
      if (tries == 0):
        print "[" + str(index) + "] FAILED:", i['title']
        failed = failed + 1

      else:
        sys.stdout.write ('failed, retrying: ' + str(tries) + ' in 5 secs\n')
        tries = tries - 1
        time.sleep(5)

  index = index + 1

print "Finished, completed:", (index - offset), "failed:", failed, "of total:", len(items)